© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 25449
    Prev
    Next
    INDEX
    Explanations

    scrub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athe
    -0.07
     Idea
    -0.06
     awkward
    -0.06
    účast
    -0.06
     tablespoon
    -0.06
    osp
    -0.06
    inp
    -0.06
     إلا
    -0.06
     coraz
    -0.06
    개를
    -0.06
    POSITIVE LOGITS
     Enrollment
    0.07
    _questions
    0.07
     }(
    0.07
     }
    0.07
    States
    0.06
    ClickListener
    0.06
    pl
    0.06
    Target
    0.06
    ~=
    0.06
     Python
    0.06
    Activations Density 0.000%

    No Known Activations